Hugging Face's logo

boltuix
/
EntityBERT

Token Classification
Transformers
Safetensors
English
bert
ner
named-entity-recognition
text-classification
transformer
pretrained-model
huggingface
real-time-inference
efficient-nlp
micro-nlp
chatbot
information-extraction
document-understanding
search-enhancement
medical-nlp
financial-nlp
legal-nlp
general-purpose-nlp
on-device-nlp
Model card Files Community
boltuix commited on
Commit
b1b350b
·
verified ·
1 Parent(s): 3e9be6a

Upload 6 files

Browse files
Files changed (6) hide show
  1. config.json +114 -0
  2. model.safetensors +3 -0
  3. special_tokens_map.json +37 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +58 -0
  6. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 128,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2",
14
+ "3": "LABEL_3",
15
+ "4": "LABEL_4",
16
+ "5": "LABEL_5",
17
+ "6": "LABEL_6",
18
+ "7": "LABEL_7",
19
+ "8": "LABEL_8",
20
+ "9": "LABEL_9",
21
+ "10": "LABEL_10",
22
+ "11": "LABEL_11",
23
+ "12": "LABEL_12",
24
+ "13": "LABEL_13",
25
+ "14": "LABEL_14",
26
+ "15": "LABEL_15",
27
+ "16": "LABEL_16",
28
+ "17": "LABEL_17",
29
+ "18": "LABEL_18",
30
+ "19": "LABEL_19",
31
+ "20": "LABEL_20",
32
+ "21": "LABEL_21",
33
+ "22": "LABEL_22",
34
+ "23": "LABEL_23",
35
+ "24": "LABEL_24",
36
+ "25": "LABEL_25",
37
+ "26": "LABEL_26",
38
+ "27": "LABEL_27",
39
+ "28": "LABEL_28",
40
+ "29": "LABEL_29",
41
+ "30": "LABEL_30",
42
+ "31": "LABEL_31",
43
+ "32": "LABEL_32",
44
+ "33": "LABEL_33",
45
+ "34": "LABEL_34",
46
+ "35": "LABEL_35",
47
+ "36": "LABEL_36",
48
+ "37": "LABEL_37",
49
+ "38": "LABEL_38",
50
+ "39": "LABEL_39",
51
+ "40": "LABEL_40",
52
+ "41": "LABEL_41",
53
+ "42": "LABEL_42"
54
+ },
55
+ "initializer_range": 0.02,
56
+ "intermediate_size": 512,
57
+ "label2id": {
58
+ "LABEL_0": 0,
59
+ "LABEL_1": 1,
60
+ "LABEL_10": 10,
61
+ "LABEL_11": 11,
62
+ "LABEL_12": 12,
63
+ "LABEL_13": 13,
64
+ "LABEL_14": 14,
65
+ "LABEL_15": 15,
66
+ "LABEL_16": 16,
67
+ "LABEL_17": 17,
68
+ "LABEL_18": 18,
69
+ "LABEL_19": 19,
70
+ "LABEL_2": 2,
71
+ "LABEL_20": 20,
72
+ "LABEL_21": 21,
73
+ "LABEL_22": 22,
74
+ "LABEL_23": 23,
75
+ "LABEL_24": 24,
76
+ "LABEL_25": 25,
77
+ "LABEL_26": 26,
78
+ "LABEL_27": 27,
79
+ "LABEL_28": 28,
80
+ "LABEL_29": 29,
81
+ "LABEL_3": 3,
82
+ "LABEL_30": 30,
83
+ "LABEL_31": 31,
84
+ "LABEL_32": 32,
85
+ "LABEL_33": 33,
86
+ "LABEL_34": 34,
87
+ "LABEL_35": 35,
88
+ "LABEL_36": 36,
89
+ "LABEL_37": 37,
90
+ "LABEL_38": 38,
91
+ "LABEL_39": 39,
92
+ "LABEL_4": 4,
93
+ "LABEL_40": 40,
94
+ "LABEL_41": 41,
95
+ "LABEL_42": 42,
96
+ "LABEL_5": 5,
97
+ "LABEL_6": 6,
98
+ "LABEL_7": 7,
99
+ "LABEL_8": 8,
100
+ "LABEL_9": 9
101
+ },
102
+ "layer_norm_eps": 1e-12,
103
+ "max_position_embeddings": 512,
104
+ "model_type": "bert",
105
+ "num_attention_heads": 2,
106
+ "num_hidden_layers": 4,
107
+ "pad_token_id": 0,
108
+ "position_embedding_type": "absolute",
109
+ "torch_dtype": "float32",
110
+ "transformers_version": "4.52.4",
111
+ "type_vocab_size": 2,
112
+ "use_cache": true,
113
+ "vocab_size": 30522
114
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3a0dca31f158f7989a2864be297514abb348edf70699c83b6c08ab1c5d2b47f
3
+ size 19094108
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff