Hugging Face's logo

PuxAI
/
GenPII-framework_CRF

Safetensors
Model card Files
xet
 Community
PuxAI commited on
Commit
83f9587
·
verified ·
1 Parent(s): 13f04ed

Train 10k + CRF for gretel-pii-ready-augmented. F1: 0.9588

Browse files
Files changed (6) hide show
  1. gretel-pii-ready-augmented/TokenBased-BERT/model.safetensors +3 -0
  2. gretel-pii-ready-augmented/TokenBased-BERT/special_tokens_map.json +37 -0
  3. gretel-pii-ready-augmented/TokenBased-BERT/tokenizer.json +0 -0
  4. gretel-pii-ready-augmented/TokenBased-BERT/tokenizer_config.json +66 -0
  5. gretel-pii-ready-augmented/TokenBased-BERT/training_args.bin +3 -0
  6. gretel-pii-ready-augmented/TokenBased-BERT/vocab.txt +0 -0
gretel-pii-ready-augmented/TokenBased-BERT/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abf869ea4474b6cd63bbb6bd1504658bd30d47649cbd76474545b3185e9e2525
3
+ size 711721104
gretel-pii-ready-augmented/TokenBased-BERT/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
+ }
gretel-pii-ready-augmented/TokenBased-BERT/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
gretel-pii-ready-augmented/TokenBased-BERT/tokenizer_config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "100": {
13
+ "content": "[UNK]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "101": {
21
+ "content": "[CLS]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "102": {
29
+ "content": "[SEP]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "103": {
37
+ "content": "[MASK]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "backend": "tokenizers",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "[CLS]",
48
+ "do_lower_case": false,
49
+ "extra_special_tokens": {},
50
+ "is_local": false,
51
+ "mask_token": "[MASK]",
52
+ "max_length": 512,
53
+ "model_max_length": 512,
54
+ "pad_to_multiple_of": null,
55
+ "pad_token": "[PAD]",
56
+ "pad_token_type_id": 0,
57
+ "padding_side": "right",
58
+ "sep_token": "[SEP]",
59
+ "stride": 0,
60
+ "strip_accents": null,
61
+ "tokenize_chinese_chars": true,
62
+ "tokenizer_class": "BertTokenizer",
63
+ "truncation_side": "right",
64
+ "truncation_strategy": "longest_first",
65
+ "unk_token": "[UNK]"
66
+ }
gretel-pii-ready-augmented/TokenBased-BERT/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47873b161c6dfaca1defafe7a4910b44f178b7c32e37d60e350d2ae6ecbdd7dc
3
+ size 5777
gretel-pii-ready-augmented/TokenBased-BERT/vocab.txt ADDED
The diff for this file is too large to render. See raw diff