Hugging Face's logo

Sifr-un
/
bert-large-uncased-LMD

Token Classification
Transformers
Safetensors
bert
Inference Endpoints
Model card Files Community
Sifr-un commited on
Commit
57947b4
•
1 Parent(s): 4ef99bb

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. config.json +126 -0
  2. model.safetensors +3 -0
  3. special_tokens_map.json +7 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +55 -0
config.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-large-uncased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "L-CNTY",
14
+ "1": "I-HPOI",
15
+ "2": "B-DIST",
16
+ "3": "U-STAT",
17
+ "4": "L-CTRY",
18
+ "5": "B-HPOI",
19
+ "6": "I-ST",
20
+ "7": "I-STAT",
21
+ "8": "U-CNTY",
22
+ "9": "L-CONT",
23
+ "10": "B-STAT",
24
+ "11": "U-OTHR",
25
+ "12": "O",
26
+ "13": "B-CITY",
27
+ "14": "L-NBHD",
28
+ "15": "L-HPOI",
29
+ "16": "B-CTRY",
30
+ "17": "U-DIST",
31
+ "18": "I-NPOI",
32
+ "19": "U-CITY",
33
+ "20": "U-ISL",
34
+ "21": "U-NBHD",
35
+ "22": "B-ST",
36
+ "23": "U-HPOI",
37
+ "24": "I-ISL",
38
+ "25": "I-DIST",
39
+ "26": "U-CTRY",
40
+ "27": "B-ISL",
41
+ "28": "B-NPOI",
42
+ "29": "L-DIST",
43
+ "30": "L-ISL",
44
+ "31": "I-CITY",
45
+ "32": "L-ST",
46
+ "33": "U-CONT",
47
+ "34": "U-NPOI",
48
+ "35": "L-STAT",
49
+ "36": "I-CNTY",
50
+ "37": "L-NPOI",
51
+ "38": "B-CONT",
52
+ "39": "B-CNTY",
53
+ "40": "I-OTHR",
54
+ "41": "B-NBHD",
55
+ "42": "U-ST",
56
+ "43": "L-CITY",
57
+ "44": "L-OTHR",
58
+ "45": "I-CTRY",
59
+ "46": "I-NBHD",
60
+ "47": "B-OTHR"
61
+ },
62
+ "initializer_range": 0.02,
63
+ "intermediate_size": 4096,
64
+ "label2id": {
65
+ "B-CITY": 13,
66
+ "B-CNTY": 39,
67
+ "B-CONT": 38,
68
+ "B-CTRY": 16,
69
+ "B-DIST": 2,
70
+ "B-HPOI": 5,
71
+ "B-ISL": 27,
72
+ "B-NBHD": 41,
73
+ "B-NPOI": 28,
74
+ "B-OTHR": 47,
75
+ "B-ST": 22,
76
+ "B-STAT": 10,
77
+ "I-CITY": 31,
78
+ "I-CNTY": 36,
79
+ "I-CTRY": 45,
80
+ "I-DIST": 25,
81
+ "I-HPOI": 1,
82
+ "I-ISL": 24,
83
+ "I-NBHD": 46,
84
+ "I-NPOI": 18,
85
+ "I-OTHR": 40,
86
+ "I-ST": 6,
87
+ "I-STAT": 7,
88
+ "L-CITY": 43,
89
+ "L-CNTY": 0,
90
+ "L-CONT": 9,
91
+ "L-CTRY": 4,
92
+ "L-DIST": 29,
93
+ "L-HPOI": 15,
94
+ "L-ISL": 30,
95
+ "L-NBHD": 14,
96
+ "L-NPOI": 37,
97
+ "L-OTHR": 44,
98
+ "L-ST": 32,
99
+ "L-STAT": 35,
100
+ "O": 12,
101
+ "U-CITY": 19,
102
+ "U-CNTY": 8,
103
+ "U-CONT": 33,
104
+ "U-CTRY": 26,
105
+ "U-DIST": 17,
106
+ "U-HPOI": 23,
107
+ "U-ISL": 20,
108
+ "U-NBHD": 21,
109
+ "U-NPOI": 34,
110
+ "U-OTHR": 11,
111
+ "U-ST": 42,
112
+ "U-STAT": 3
113
+ },
114
+ "layer_norm_eps": 1e-12,
115
+ "max_position_embeddings": 512,
116
+ "model_type": "bert",
117
+ "num_attention_heads": 16,
118
+ "num_hidden_layers": 24,
119
+ "pad_token_id": 0,
120
+ "position_embedding_type": "absolute",
121
+ "torch_dtype": "float32",
122
+ "transformers_version": "4.44.2",
123
+ "type_vocab_size": 2,
124
+ "use_cache": true,
125
+ "vocab_size": 30522
126
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b21658dd2e4a06f0c9b80a9e68d8e303eb6babae516431d2c21b4911c86e925c
3
+ size 1336612768
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": true,
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
+ }