Hugging Face's logo

Xenova
/
transformers.js

ONNX
Model card Files Community
2
Joshua Lochner commited on
Commit
5985633
•
1 Parent(s): b52fd9e

Add models for token classification

Browse files
Files changed (36) hide show
  1. quantized/Davlan/bert-base-multilingual-cased-ner-hrl/token-classification/config.json +46 -0
  2. quantized/Davlan/bert-base-multilingual-cased-ner-hrl/token-classification/model.onnx +3 -0
  3. quantized/Davlan/bert-base-multilingual-cased-ner-hrl/token-classification/special_tokens_map.json +7 -0
  4. quantized/Davlan/bert-base-multilingual-cased-ner-hrl/token-classification/tokenizer.json +0 -0
  5. quantized/Davlan/bert-base-multilingual-cased-ner-hrl/token-classification/tokenizer_config.json +15 -0
  6. quantized/Davlan/bert-base-multilingual-cased-ner-hrl/token-classification/vocab.txt +0 -0
  7. quantized/ckiplab/bert-base-chinese-ner/token-classification/config.json +182 -0
  8. quantized/ckiplab/bert-base-chinese-ner/token-classification/model.onnx +3 -0
  9. quantized/ckiplab/bert-base-chinese-ner/token-classification/special_tokens_map.json +7 -0
  10. quantized/ckiplab/bert-base-chinese-ner/token-classification/tokenizer.json +0 -0
  11. quantized/ckiplab/bert-base-chinese-ner/token-classification/tokenizer_config.json +15 -0
  12. quantized/ckiplab/bert-base-chinese-ner/token-classification/vocab.txt +0 -0
  13. quantized/ckiplab/bert-base-chinese-pos/token-classification/config.json +156 -0
  14. quantized/ckiplab/bert-base-chinese-pos/token-classification/model.onnx +3 -0
  15. quantized/ckiplab/bert-base-chinese-pos/token-classification/special_tokens_map.json +7 -0
  16. quantized/ckiplab/bert-base-chinese-pos/token-classification/tokenizer.json +0 -0
  17. quantized/ckiplab/bert-base-chinese-pos/token-classification/tokenizer_config.json +15 -0
  18. quantized/ckiplab/bert-base-chinese-pos/token-classification/vocab.txt +0 -0
  19. quantized/ckiplab/bert-base-chinese-ws/token-classification/config.json +40 -0
  20. quantized/ckiplab/bert-base-chinese-ws/token-classification/model.onnx +3 -0
  21. quantized/ckiplab/bert-base-chinese-ws/token-classification/special_tokens_map.json +7 -0
  22. quantized/ckiplab/bert-base-chinese-ws/token-classification/tokenizer.json +0 -0
  23. quantized/ckiplab/bert-base-chinese-ws/token-classification/tokenizer_config.json +15 -0
  24. quantized/ckiplab/bert-base-chinese-ws/token-classification/vocab.txt +0 -0
  25. quantized/dslim/bert-base-NER-uncased/token-classification/config.json +48 -0
  26. quantized/dslim/bert-base-NER-uncased/token-classification/model.onnx +3 -0
  27. quantized/dslim/bert-base-NER-uncased/token-classification/special_tokens_map.json +7 -0
  28. quantized/dslim/bert-base-NER-uncased/token-classification/tokenizer.json +0 -0
  29. quantized/dslim/bert-base-NER-uncased/token-classification/tokenizer_config.json +16 -0
  30. quantized/dslim/bert-base-NER-uncased/token-classification/vocab.txt +0 -0
  31. quantized/dslim/bert-base-NER/token-classification/config.json +48 -0
  32. quantized/dslim/bert-base-NER/token-classification/model.onnx +3 -0
  33. quantized/dslim/bert-base-NER/token-classification/special_tokens_map.json +7 -0
  34. quantized/dslim/bert-base-NER/token-classification/tokenizer.json +0 -0
  35. quantized/dslim/bert-base-NER/token-classification/tokenizer_config.json +16 -0
  36. quantized/dslim/bert-base-NER/token-classification/vocab.txt +0 -0
quantized/Davlan/bert-base-multilingual-cased-ner-hrl/token-classification/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Davlan/distilbert-base-multilingual-cased-ner-hrl",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForTokenClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "O",
13
+ "1": "B-DATE",
14
+ "2": "I-DATE",
15
+ "3": "B-PER",
16
+ "4": "I-PER",
17
+ "5": "B-ORG",
18
+ "6": "I-ORG",
19
+ "7": "B-LOC",
20
+ "8": "I-LOC"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "label2id": {
24
+ "B-DATE": 1,
25
+ "B-LOC": 7,
26
+ "B-ORG": 5,
27
+ "B-PER": 3,
28
+ "I-DATE": 2,
29
+ "I-LOC": 8,
30
+ "I-ORG": 6,
31
+ "I-PER": 4,
32
+ "O": 0
33
+ },
34
+ "max_position_embeddings": 512,
35
+ "model_type": "distilbert",
36
+ "n_heads": 12,
37
+ "n_layers": 6,
38
+ "output_past": true,
39
+ "pad_token_id": 0,
40
+ "qa_dropout": 0.1,
41
+ "seq_classif_dropout": 0.2,
42
+ "sinusoidal_pos_embds": false,
43
+ "tie_weights_": true,
44
+ "transformers_version": "4.27.4",
45
+ "vocab_size": 119547
46
+ }
quantized/Davlan/bert-base-multilingual-cased-ner-hrl/token-classification/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24a0b98f4dd4cd92842f5a541272f86f760225a64a29928eddef14bdb2edb986
3
+ size 135359829
quantized/Davlan/bert-base-multilingual-cased-ner-hrl/token-classification/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
quantized/Davlan/bert-base-multilingual-cased-ner-hrl/token-classification/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
quantized/Davlan/bert-base-multilingual-cased-ner-hrl/token-classification/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": false,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "never_split": null,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "special_tokens_map_file": null,
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "DistilBertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
quantized/Davlan/bert-base-multilingual-cased-ner-hrl/token-classification/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
quantized/ckiplab/bert-base-chinese-ner/token-classification/config.json ADDED
@@ -0,0 +1,182 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ckiplab/bert-base-chinese-ner",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "B-CARDINAL",
16
+ "2": "B-DATE",
17
+ "3": "B-EVENT",
18
+ "4": "B-FAC",
19
+ "5": "B-GPE",
20
+ "6": "B-LANGUAGE",
21
+ "7": "B-LAW",
22
+ "8": "B-LOC",
23
+ "9": "B-MONEY",
24
+ "10": "B-NORP",
25
+ "11": "B-ORDINAL",
26
+ "12": "B-ORG",
27
+ "13": "B-PERCENT",
28
+ "14": "B-PERSON",
29
+ "15": "B-PRODUCT",
30
+ "16": "B-QUANTITY",
31
+ "17": "B-TIME",
32
+ "18": "B-WORK_OF_ART",
33
+ "19": "I-CARDINAL",
34
+ "20": "I-DATE",
35
+ "21": "I-EVENT",
36
+ "22": "I-FAC",
37
+ "23": "I-GPE",
38
+ "24": "I-LANGUAGE",
39
+ "25": "I-LAW",
40
+ "26": "I-LOC",
41
+ "27": "I-MONEY",
42
+ "28": "I-NORP",
43
+ "29": "I-ORDINAL",
44
+ "30": "I-ORG",
45
+ "31": "I-PERCENT",
46
+ "32": "I-PERSON",
47
+ "33": "I-PRODUCT",
48
+ "34": "I-QUANTITY",
49
+ "35": "I-TIME",
50
+ "36": "I-WORK_OF_ART",
51
+ "37": "E-CARDINAL",
52
+ "38": "E-DATE",
53
+ "39": "E-EVENT",
54
+ "40": "E-FAC",
55
+ "41": "E-GPE",
56
+ "42": "E-LANGUAGE",
57
+ "43": "E-LAW",
58
+ "44": "E-LOC",
59
+ "45": "E-MONEY",
60
+ "46": "E-NORP",
61
+ "47": "E-ORDINAL",
62
+ "48": "E-ORG",
63
+ "49": "E-PERCENT",
64
+ "50": "E-PERSON",
65
+ "51": "E-PRODUCT",
66
+ "52": "E-QUANTITY",
67
+ "53": "E-TIME",
68
+ "54": "E-WORK_OF_ART",
69
+ "55": "S-CARDINAL",
70
+ "56": "S-DATE",
71
+ "57": "S-EVENT",
72
+ "58": "S-FAC",
73
+ "59": "S-GPE",
74
+ "60": "S-LANGUAGE",
75
+ "61": "S-LAW",
76
+ "62": "S-LOC",
77
+ "63": "S-MONEY",
78
+ "64": "S-NORP",
79
+ "65": "S-ORDINAL",
80
+ "66": "S-ORG",
81
+ "67": "S-PERCENT",
82
+ "68": "S-PERSON",
83
+ "69": "S-PRODUCT",
84
+ "70": "S-QUANTITY",
85
+ "71": "S-TIME",
86
+ "72": "S-WORK_OF_ART"
87
+ },
88
+ "initializer_range": 0.02,
89
+ "intermediate_size": 3072,
90
+ "label2id": {
91
+ "B-CARDINAL": 1,
92
+ "B-DATE": 2,
93
+ "B-EVENT": 3,
94
+ "B-FAC": 4,
95
+ "B-GPE": 5,
96
+ "B-LANGUAGE": 6,
97
+ "B-LAW": 7,
98
+ "B-LOC": 8,
99
+ "B-MONEY": 9,
100
+ "B-NORP": 10,
101
+ "B-ORDINAL": 11,
102
+ "B-ORG": 12,
103
+ "B-PERCENT": 13,
104
+ "B-PERSON": 14,
105
+ "B-PRODUCT": 15,
106
+ "B-QUANTITY": 16,
107
+ "B-TIME": 17,
108
+ "B-WORK_OF_ART": 18,
109
+ "E-CARDINAL": 37,
110
+ "E-DATE": 38,
111
+ "E-EVENT": 39,
112
+ "E-FAC": 40,
113
+ "E-GPE": 41,
114
+ "E-LANGUAGE": 42,
115
+ "E-LAW": 43,
116
+ "E-LOC": 44,
117
+ "E-MONEY": 45,
118
+ "E-NORP": 46,
119
+ "E-ORDINAL": 47,
120
+ "E-ORG": 48,
121
+ "E-PERCENT": 49,
122
+ "E-PERSON": 50,
123
+ "E-PRODUCT": 51,
124
+ "E-QUANTITY": 52,
125
+ "E-TIME": 53,
126
+ "E-WORK_OF_ART": 54,
127
+ "I-CARDINAL": 19,
128
+ "I-DATE": 20,
129
+ "I-EVENT": 21,
130
+ "I-FAC": 22,
131
+ "I-GPE": 23,
132
+ "I-LANGUAGE": 24,
133
+ "I-LAW": 25,
134
+ "I-LOC": 26,
135
+ "I-MONEY": 27,
136
+ "I-NORP": 28,
137
+ "I-ORDINAL": 29,
138
+ "I-ORG": 30,
139
+ "I-PERCENT": 31,
140
+ "I-PERSON": 32,
141
+ "I-PRODUCT": 33,
142
+ "I-QUANTITY": 34,
143
+ "I-TIME": 35,
144
+ "I-WORK_OF_ART": 36,
145
+ "O": 0,
146
+ "S-CARDINAL": 55,
147
+ "S-DATE": 56,
148
+ "S-EVENT": 57,
149
+ "S-FAC": 58,
150
+ "S-GPE": 59,
151
+ "S-LANGUAGE": 60,
152
+ "S-LAW": 61,
153
+ "S-LOC": 62,
154
+ "S-MONEY": 63,
155
+ "S-NORP": 64,
156
+ "S-ORDINAL": 65,
157
+ "S-ORG": 66,
158
+ "S-PERCENT": 67,
159
+ "S-PERSON": 68,
160
+ "S-PRODUCT": 69,
161
+ "S-QUANTITY": 70,
162
+ "S-TIME": 71,
163
+ "S-WORK_OF_ART": 72
164
+ },
165
+ "layer_norm_eps": 1e-12,
166
+ "max_position_embeddings": 512,
167
+ "model_type": "bert",
168
+ "num_attention_heads": 12,
169
+ "num_hidden_layers": 12,
170
+ "pad_token_id": 0,
171
+ "pooler_fc_size": 768,
172
+ "pooler_num_attention_heads": 12,
173
+ "pooler_num_fc_layers": 3,
174
+ "pooler_size_per_head": 128,
175
+ "pooler_type": "first_token_transform",
176
+ "position_embedding_type": "absolute",
177
+ "tokenizer_class": "BertTokenizerFast",
178
+ "transformers_version": "4.27.4",
179
+ "type_vocab_size": 2,
180
+ "use_cache": true,
181
+ "vocab_size": 21128
182
+ }
quantized/ckiplab/bert-base-chinese-ner/token-classification/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f8e1a4dac9c65d880b41c8ebedda02f074536f5ab249bdae66cfe41ae709dee
3
+ size 102959365
quantized/ckiplab/bert-base-chinese-ner/token-classification/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
quantized/ckiplab/bert-base-chinese-ner/token-classification/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
quantized/ckiplab/bert-base-chinese-ner/token-classification/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": false,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "never_split": null,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "special_tokens_map_file": null,
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
quantized/ckiplab/bert-base-chinese-ner/token-classification/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
quantized/ckiplab/bert-base-chinese-pos/token-classification/config.json ADDED
@@ -0,0 +1,156 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ckiplab/bert-base-chinese-pos",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "A",
15
+ "1": "Caa",
16
+ "2": "Cab",
17
+ "3": "Cba",
18
+ "4": "Cbb",
19
+ "5": "D",
20
+ "6": "Da",
21
+ "7": "Dfa",
22
+ "8": "Dfb",
23
+ "9": "Di",
24
+ "10": "Dk",
25
+ "11": "DM",
26
+ "12": "I",
27
+ "13": "Na",
28
+ "14": "Nb",
29
+ "15": "Nc",
30
+ "16": "Ncd",
31
+ "17": "Nd",
32
+ "18": "Nep",
33
+ "19": "Neqa",
34
+ "20": "Neqb",
35
+ "21": "Nes",
36
+ "22": "Neu",
37
+ "23": "Nf",
38
+ "24": "Ng",
39
+ "25": "Nh",
40
+ "26": "Nv",
41
+ "27": "P",
42
+ "28": "T",
43
+ "29": "VA",
44
+ "30": "VAC",
45
+ "31": "VB",
46
+ "32": "VC",
47
+ "33": "VCL",
48
+ "34": "VD",
49
+ "35": "VF",
50
+ "36": "VE",
51
+ "37": "VG",
52
+ "38": "VH",
53
+ "39": "VHC",
54
+ "40": "VI",
55
+ "41": "VJ",
56
+ "42": "VK",
57
+ "43": "VL",
58
+ "44": "V_2",
59
+ "45": "DE",
60
+ "46": "SHI",
61
+ "47": "FW",
62
+ "48": "COLONCATEGORY",
63
+ "49": "COMMACATEGORY",
64
+ "50": "DASHCATEGORY",
65
+ "51": "DOTCATEGORY",
66
+ "52": "ETCCATEGORY",
67
+ "53": "EXCLAMATIONCATEGORY",
68
+ "54": "PARENTHESISCATEGORY",
69
+ "55": "PAUSECATEGORY",
70
+ "56": "PERIODCATEGORY",
71
+ "57": "QUESTIONCATEGORY",
72
+ "58": "SEMICOLONCATEGORY",
73
+ "59": "SPCHANGECATEGORY"
74
+ },
75
+ "initializer_range": 0.02,
76
+ "intermediate_size": 3072,
77
+ "label2id": {
78
+ "A": 0,
79
+ "COLONCATEGORY": 48,
80
+ "COMMACATEGORY": 49,
81
+ "Caa": 1,
82
+ "Cab": 2,
83
+ "Cba": 3,
84
+ "Cbb": 4,
85
+ "D": 5,
86
+ "DASHCATEGORY": 50,
87
+ "DE": 45,
88
+ "DM": 11,
89
+ "DOTCATEGORY": 51,
90
+ "Da": 6,
91
+ "Dfa": 7,
92
+ "Dfb": 8,
93
+ "Di": 9,
94
+ "Dk": 10,
95
+ "ETCCATEGORY": 52,
96
+ "EXCLAMATIONCATEGORY": 53,
97
+ "FW": 47,
98
+ "I": 12,
99
+ "Na": 13,
100
+ "Nb": 14,
101
+ "Nc": 15,
102
+ "Ncd": 16,
103
+ "Nd": 17,
104
+ "Nep": 18,
105
+ "Neqa": 19,
106
+ "Neqb": 20,
107
+ "Nes": 21,
108
+ "Neu": 22,
109
+ "Nf": 23,
110
+ "Ng": 24,
111
+ "Nh": 25,
112
+ "Nv": 26,
113
+ "P": 27,
114
+ "PARENTHESISCATEGORY": 54,
115
+ "PAUSECATEGORY": 55,
116
+ "PERIODCATEGORY": 56,
117
+ "QUESTIONCATEGORY": 57,
118
+ "SEMICOLONCATEGORY": 58,
119
+ "SHI": 46,
120
+ "SPCHANGECATEGORY": 59,
121
+ "T": 28,
122
+ "VA": 29,
123
+ "VAC": 30,
124
+ "VB": 31,
125
+ "VC": 32,
126
+ "VCL": 33,
127
+ "VD": 34,
128
+ "VE": 36,
129
+ "VF": 35,
130
+ "VG": 37,
131
+ "VH": 38,
132
+ "VHC": 39,
133
+ "VI": 40,
134
+ "VJ": 41,
135
+ "VK": 42,
136
+ "VL": 43,
137
+ "V_2": 44
138
+ },
139
+ "layer_norm_eps": 1e-12,
140
+ "max_position_embeddings": 512,
141
+ "model_type": "bert",
142
+ "num_attention_heads": 12,
143
+ "num_hidden_layers": 12,
144
+ "pad_token_id": 0,
145
+ "pooler_fc_size": 768,
146
+ "pooler_num_attention_heads": 12,
147
+ "pooler_num_fc_layers": 3,
148
+ "pooler_size_per_head": 128,
149
+ "pooler_type": "first_token_transform",
150
+ "position_embedding_type": "absolute",
151
+ "tokenizer_class": "BertTokenizerFast",
152
+ "transformers_version": "4.27.4",
153
+ "type_vocab_size": 2,
154
+ "use_cache": true,
155
+ "vocab_size": 21128
156
+ }
quantized/ckiplab/bert-base-chinese-pos/token-classification/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:573667749bd5372c3989418530f1f45f8b0c07274100d04f1be8bc542f42afc2
3
+ size 102949264
quantized/ckiplab/bert-base-chinese-pos/token-classification/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
quantized/ckiplab/bert-base-chinese-pos/token-classification/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
quantized/ckiplab/bert-base-chinese-pos/token-classification/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": false,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "never_split": null,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "special_tokens_map_file": null,
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
quantized/ckiplab/bert-base-chinese-pos/token-classification/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
quantized/ckiplab/bert-base-chinese-ws/token-classification/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ckiplab/bert-base-chinese-ws",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "B",
15
+ "1": "I"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "B": 0,
21
+ "I": 1
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "pooler_fc_size": 768,
30
+ "pooler_num_attention_heads": 12,
31
+ "pooler_num_fc_layers": 3,
32
+ "pooler_size_per_head": 128,
33
+ "pooler_type": "first_token_transform",
34
+ "position_embedding_type": "absolute",
35
+ "tokenizer_class": "BertTokenizerFast",
36
+ "transformers_version": "4.27.4",
37
+ "type_vocab_size": 2,
38
+ "use_cache": true,
39
+ "vocab_size": 21128
40
+ }
quantized/ckiplab/bert-base-chinese-ws/token-classification/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2542c321f98874c127811e04a1b685673feb0c252d7706a494a8956ba11c0297
3
+ size 102904192
quantized/ckiplab/bert-base-chinese-ws/token-classification/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
quantized/ckiplab/bert-base-chinese-ws/token-classification/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
quantized/ckiplab/bert-base-chinese-ws/token-classification/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": false,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "never_split": null,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "special_tokens_map_file": null,
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
quantized/ckiplab/bert-base-chinese-ws/token-classification/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
quantized/dslim/bert-base-NER-uncased/token-classification/config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dslim/bert-base-NER-uncased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "eos_token_ids": null,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "B-MISC",
15
+ "2": "I-MISC",
16
+ "3": "B-PER",
17
+ "4": "I-PER",
18
+ "5": "B-ORG",
19
+ "6": "I-ORG",
20
+ "7": "B-LOC",
21
+ "8": "I-LOC"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "B-LOC": 7,
27
+ "B-MISC": 1,
28
+ "B-ORG": 5,
29
+ "B-PER": 3,
30
+ "I-LOC": 8,
31
+ "I-MISC": 2,
32
+ "I-ORG": 6,
33
+ "I-PER": 4,
34
+ "O": 0
35
+ },
36
+ "layer_norm_eps": 1e-12,
37
+ "max_position_embeddings": 512,
38
+ "model_type": "bert",
39
+ "num_attention_heads": 12,
40
+ "num_hidden_layers": 12,
41
+ "output_past": true,
42
+ "pad_token_id": 0,
43
+ "position_embedding_type": "absolute",
44
+ "transformers_version": "4.27.4",
45
+ "type_vocab_size": 2,
46
+ "use_cache": true,
47
+ "vocab_size": 30522
48
+ }
quantized/dslim/bert-base-NER-uncased/token-classification/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba46b8ec55dd7432d2e46b2e600f2b1dc84ecf10a58a73f1b96c981de7af7b61
3
+ size 110124223
quantized/dslim/bert-base-NER-uncased/token-classification/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
quantized/dslim/bert-base-NER-uncased/token-classification/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
quantized/dslim/bert-base-NER-uncased/token-classification/tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "max_len": 512,
7
+ "model_max_length": 512,
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "special_tokens_map_file": null,
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
quantized/dslim/bert-base-NER-uncased/token-classification/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
quantized/dslim/bert-base-NER/token-classification/config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dslim/bert-base-NER",
3
+ "_num_labels": 9,
4
+ "architectures": [
5
+ "BertForTokenClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "B-MISC",
15
+ "2": "I-MISC",
16
+ "3": "B-PER",
17
+ "4": "I-PER",
18
+ "5": "B-ORG",
19
+ "6": "I-ORG",
20
+ "7": "B-LOC",
21
+ "8": "I-LOC"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "B-LOC": 7,
27
+ "B-MISC": 1,
28
+ "B-ORG": 5,
29
+ "B-PER": 3,
30
+ "I-LOC": 8,
31
+ "I-MISC": 2,
32
+ "I-ORG": 6,
33
+ "I-PER": 4,
34
+ "O": 0
35
+ },
36
+ "layer_norm_eps": 1e-12,
37
+ "max_position_embeddings": 512,
38
+ "model_type": "bert",
39
+ "num_attention_heads": 12,
40
+ "num_hidden_layers": 12,
41
+ "output_past": true,
42
+ "pad_token_id": 0,
43
+ "position_embedding_type": "absolute",
44
+ "transformers_version": "4.27.4",
45
+ "type_vocab_size": 2,
46
+ "use_cache": true,
47
+ "vocab_size": 28996
48
+ }
quantized/dslim/bert-base-NER/token-classification/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caaee70a5518ec7f9e46e5308fcc9263a8c227703a9ce46cf61c69a552349648
3
+ size 108952255
quantized/dslim/bert-base-NER/token-classification/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
quantized/dslim/bert-base-NER/token-classification/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
quantized/dslim/bert-base-NER/token-classification/tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": false,
5
+ "mask_token": "[MASK]",
6
+ "max_len": 512,
7
+ "model_max_length": 512,
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "special_tokens_map_file": null,
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
quantized/dslim/bert-base-NER/token-classification/vocab.txt ADDED
The diff for this file is too large to render. See raw diff