Hugging Face's logo

Gherman
/
bert-base-NER-Russian

Token Classification
Transformers
Safetensors
Russian
bert
Inference Endpoints
Model card Files Community
Gherman commited on
Commit
fb3c3d8
·
verified ·
1 Parent(s): 93f685e

Upload 6 files

Browse files
Files changed (6) hide show
  1. config.json +103 -0
  2. model.safetensors +3 -0
  3. special_tokens_map.json +7 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +55 -0
  6. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-multilingual-cased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "B-FIRST_NAME",
14
+ "1": "I-HOUSE",
15
+ "2": "U-FIRST_NAME",
16
+ "3": "L-FIRST_NAME",
17
+ "4": "B-CITY",
18
+ "5": "B-STREET",
19
+ "6": "L-DISTRICT",
20
+ "7": "U-REGION",
21
+ "8": "I-REGION",
22
+ "9": "U-LAST_NAME",
23
+ "10": "I-STREET",
24
+ "11": "U-CITY",
25
+ "12": "L-CITY",
26
+ "13": "U-HOUSE",
27
+ "14": "U-COUNTRY",
28
+ "15": "B-COUNTRY",
29
+ "16": "B-HOUSE",
30
+ "17": "L-MIDDLE_NAME",
31
+ "18": "L-COUNTRY",
32
+ "19": "B-MIDDLE_NAME",
33
+ "20": "B-DISTRICT",
34
+ "21": "U-MIDDLE_NAME",
35
+ "22": "O",
36
+ "23": "B-REGION",
37
+ "24": "U-STREET",
38
+ "25": "L-HOUSE",
39
+ "26": "U-DISTRICT",
40
+ "27": "L-STREET",
41
+ "28": "I-CITY",
42
+ "29": "L-REGION",
43
+ "30": "L-LAST_NAME",
44
+ "31": "I-COUNTRY",
45
+ "32": "I-LAST_NAME",
46
+ "33": "B-LAST_NAME"
47
+ },
48
+ "initializer_range": 0.02,
49
+ "intermediate_size": 3072,
50
+ "label2id": {
51
+ "B-CITY": 4,
52
+ "B-COUNTRY": 15,
53
+ "B-DISTRICT": 20,
54
+ "B-FIRST_NAME": 0,
55
+ "B-HOUSE": 16,
56
+ "B-LAST_NAME": 33,
57
+ "B-MIDDLE_NAME": 19,
58
+ "B-REGION": 23,
59
+ "B-STREET": 5,
60
+ "I-CITY": 28,
61
+ "I-COUNTRY": 31,
62
+ "I-HOUSE": 1,
63
+ "I-LAST_NAME": 32,
64
+ "I-REGION": 8,
65
+ "I-STREET": 10,
66
+ "L-CITY": 12,
67
+ "L-COUNTRY": 18,
68
+ "L-DISTRICT": 6,
69
+ "L-FIRST_NAME": 3,
70
+ "L-HOUSE": 25,
71
+ "L-LAST_NAME": 30,
72
+ "L-MIDDLE_NAME": 17,
73
+ "L-REGION": 29,
74
+ "L-STREET": 27,
75
+ "O": 22,
76
+ "U-CITY": 11,
77
+ "U-COUNTRY": 14,
78
+ "U-DISTRICT": 26,
79
+ "U-FIRST_NAME": 2,
80
+ "U-HOUSE": 13,
81
+ "U-LAST_NAME": 9,
82
+ "U-MIDDLE_NAME": 21,
83
+ "U-REGION": 7,
84
+ "U-STREET": 24
85
+ },
86
+ "layer_norm_eps": 1e-12,
87
+ "max_position_embeddings": 512,
88
+ "model_type": "bert",
89
+ "num_attention_heads": 12,
90
+ "num_hidden_layers": 12,
91
+ "pad_token_id": 0,
92
+ "pooler_fc_size": 768,
93
+ "pooler_num_attention_heads": 12,
94
+ "pooler_num_fc_layers": 3,
95
+ "pooler_size_per_head": 128,
96
+ "pooler_type": "first_token_transform",
97
+ "position_embedding_type": "absolute",
98
+ "torch_dtype": "float32",
99
+ "transformers_version": "4.44.2",
100
+ "type_vocab_size": 2,
101
+ "use_cache": true,
102
+ "vocab_size": 119547
103
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db622cca205f1dc09ccaa2f8fab3243e70c34e8995c6fc7cbfb529aff2363a46
3
+ size 709179336
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff