Hugging Face's logo

somukandula
/
maskara-tiny-v2

Token Classification
Transformers
Safetensors
bert
Generated from Trainer
Model card Files
xet
 Community
somukandula commited on
Commit
177d05f
·
verified ·
1 Parent(s): 5b4feb7

Training in progress, step 1000

Browse files
Files changed (7) hide show
  1. config.json +100 -0
  2. model.safetensors +3 -0
  3. special_tokens_map.json +37 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +61 -0
  6. training_args.bin +3 -0
  7. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "somukandula/maskara-tiny",
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": 384,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "B-ADDRESS",
15
+ "2": "B-API_KEY",
16
+ "3": "B-CREDIT_CARD",
17
+ "4": "B-DATE_OF_BIRTH",
18
+ "5": "B-DRIVER_LICENSE",
19
+ "6": "B-EMAIL",
20
+ "7": "B-IP_ADDRESS",
21
+ "8": "B-PASSWORD",
22
+ "9": "B-PERSON_NAME",
23
+ "10": "B-PHONE",
24
+ "11": "B-SSN",
25
+ "12": "B-USERNAME",
26
+ "13": "B-AADHAAR",
27
+ "14": "B-PAN_CARD",
28
+ "15": "B-PASSPORT",
29
+ "16": "B-UPI_ID",
30
+ "17": "B-VEHICLE_REG",
31
+ "18": "I-ADDRESS",
32
+ "19": "I-API_KEY",
33
+ "20": "I-CREDIT_CARD",
34
+ "21": "I-DATE_OF_BIRTH",
35
+ "22": "I-DRIVER_LICENSE",
36
+ "23": "I-EMAIL",
37
+ "24": "I-IP_ADDRESS",
38
+ "25": "I-PASSWORD",
39
+ "26": "I-PERSON_NAME",
40
+ "27": "I-PHONE",
41
+ "28": "I-SSN",
42
+ "29": "I-USERNAME",
43
+ "30": "I-AADHAAR",
44
+ "31": "I-PAN_CARD",
45
+ "32": "I-PASSPORT",
46
+ "33": "I-UPI_ID",
47
+ "34": "I-VEHICLE_REG"
48
+ },
49
+ "initializer_range": 0.02,
50
+ "intermediate_size": 1536,
51
+ "label2id": {
52
+ "B-AADHAAR": 13,
53
+ "B-ADDRESS": 1,
54
+ "B-API_KEY": 2,
55
+ "B-CREDIT_CARD": 3,
56
+ "B-DATE_OF_BIRTH": 4,
57
+ "B-DRIVER_LICENSE": 5,
58
+ "B-EMAIL": 6,
59
+ "B-IP_ADDRESS": 7,
60
+ "B-PAN_CARD": 14,
61
+ "B-PASSPORT": 15,
62
+ "B-PASSWORD": 8,
63
+ "B-PERSON_NAME": 9,
64
+ "B-PHONE": 10,
65
+ "B-SSN": 11,
66
+ "B-UPI_ID": 16,
67
+ "B-USERNAME": 12,
68
+ "B-VEHICLE_REG": 17,
69
+ "I-AADHAAR": 30,
70
+ "I-ADDRESS": 18,
71
+ "I-API_KEY": 19,
72
+ "I-CREDIT_CARD": 20,
73
+ "I-DATE_OF_BIRTH": 21,
74
+ "I-DRIVER_LICENSE": 22,
75
+ "I-EMAIL": 23,
76
+ "I-IP_ADDRESS": 24,
77
+ "I-PAN_CARD": 31,
78
+ "I-PASSPORT": 32,
79
+ "I-PASSWORD": 25,
80
+ "I-PERSON_NAME": 26,
81
+ "I-PHONE": 27,
82
+ "I-SSN": 28,
83
+ "I-UPI_ID": 33,
84
+ "I-USERNAME": 29,
85
+ "I-VEHICLE_REG": 34,
86
+ "O": 0
87
+ },
88
+ "layer_norm_eps": 1e-12,
89
+ "max_position_embeddings": 512,
90
+ "model_type": "bert",
91
+ "num_attention_heads": 12,
92
+ "num_hidden_layers": 6,
93
+ "pad_token_id": 0,
94
+ "position_embedding_type": "absolute",
95
+ "torch_dtype": "float32",
96
+ "transformers_version": "4.44.2",
97
+ "type_vocab_size": 2,
98
+ "use_cache": true,
99
+ "vocab_size": 30522
100
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfb2746fb1a4e38177ae385dacdda295475eda3bdc8a94546b22483443f1387a
3
+ size 90327228
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 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "mask_token": "[MASK]",
49
+ "max_length": 512,
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "stride": 0,
55
+ "strip_accents": null,
56
+ "tokenize_chinese_chars": true,
57
+ "tokenizer_class": "BertTokenizer",
58
+ "truncation_side": "right",
59
+ "truncation_strategy": "longest_first",
60
+ "unk_token": "[UNK]"
61
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d6c93de8cd37d7e0260dfd6693acf236ba432f257259df6b72553729b41ed6e
3
+ size 5176
vocab.txt ADDED
The diff for this file is too large to render. See raw diff