Hugging Face's logo

PuxAI
/
PII-Binary-Filter-Extreme-Recall

Text Classification
Transformers
Safetensors
deberta-v2
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
PuxAI commited on
Commit
3cc3ea2
·
verified ·
1 Parent(s): f13dea3

Training in progress, epoch 1

Browse files
Files changed (8) hide show
  1. added_tokens.json +5 -0
  2. config.json +45 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +31 -0
  5. spm.model +3 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +79 -0
  8. training_args.bin +3 -0
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "[/E1]": 128002,
3
+ "[E1]": 128001,
4
+ "[MASK]": 128000
5
+ }
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaV2ForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 1,
7
+ "dtype": "float32",
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "NON_PII",
14
+ "1": "VALID_PII"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "NON_PII": 0,
20
+ "VALID_PII": 1
21
+ },
22
+ "layer_norm_eps": 1e-07,
23
+ "legacy": true,
24
+ "max_position_embeddings": 512,
25
+ "max_relative_positions": -1,
26
+ "model_type": "deberta-v2",
27
+ "norm_rel_ebd": "layer_norm",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 6,
30
+ "pad_token_id": 0,
31
+ "pooler_dropout": 0,
32
+ "pooler_hidden_act": "gelu",
33
+ "pooler_hidden_size": 768,
34
+ "pos_att_type": [
35
+ "p2c",
36
+ "c2p"
37
+ ],
38
+ "position_biased_input": false,
39
+ "position_buckets": 256,
40
+ "relative_attention": true,
41
+ "share_att_key": true,
42
+ "transformers_version": "4.56.0",
43
+ "type_vocab_size": 0,
44
+ "vocab_size": 128003
45
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e027437b4eae713dd8cc46fbb3ea5bb5bbd562fd73465180f9fa3600576f2465
3
+ size 567300568
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "[E1]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "[/E1]",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": "[CLS]",
19
+ "cls_token": "[CLS]",
20
+ "eos_token": "[SEP]",
21
+ "mask_token": "[MASK]",
22
+ "pad_token": "[PAD]",
23
+ "sep_token": "[SEP]",
24
+ "unk_token": {
25
+ "content": "[UNK]",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128001": {
44
+ "content": "[E1]",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128002": {
52
+ "content": "[/E1]",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "additional_special_tokens": [
61
+ "[E1]",
62
+ "[/E1]"
63
+ ],
64
+ "bos_token": "[CLS]",
65
+ "clean_up_tokenization_spaces": false,
66
+ "cls_token": "[CLS]",
67
+ "do_lower_case": false,
68
+ "eos_token": "[SEP]",
69
+ "extra_special_tokens": {},
70
+ "mask_token": "[MASK]",
71
+ "model_max_length": 1000000000000000019884624838656,
72
+ "pad_token": "[PAD]",
73
+ "sep_token": "[SEP]",
74
+ "sp_model_kwargs": {},
75
+ "split_by_punct": false,
76
+ "tokenizer_class": "DebertaV2Tokenizer",
77
+ "unk_token": "[UNK]",
78
+ "vocab_type": "spm"
79
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:281cfa1bbdc92455289fd2df1a29b759c36cc3a50e10a88ebae1f87c0b9bda14
3
+ size 5841