Hugging Face's logo

8Fai
/
context-filter

Token Classification
Transformers
Safetensors
English
gpt2
privacy
pii-detection
pii-redaction
sliding-window-attention
rope
swiglu
text-generation-inference
Model card Files
xet
 Community
Selennnn commited on
Commit
c4ac2f6
·
verified ·
1 Parent(s): 0d9572e

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +40 -0
  2. generation_config.json +60 -0
  3. label_map.json +56 -0
  4. model.safetensors +3 -0
  5. special_tokens_map.json +6 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +13 -0
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 50257,
3
+ "hidden_size": 512,
4
+ "num_layers": 10,
5
+ "num_q_heads": 8,
6
+ "num_kv_heads": 4,
7
+ "ffn_intermediate": 1792,
8
+ "max_seq_len": 32768,
9
+ "window_size": 512,
10
+ "rope_theta": 500000.0,
11
+ "dropout": 0.05,
12
+ "entity_types": [
13
+ "PERSON",
14
+ "EMAIL",
15
+ "PHONE",
16
+ "ADDRESS",
17
+ "SSN",
18
+ "CREDITCARD",
19
+ "IP",
20
+ "DATE",
21
+ "ORG",
22
+ "USERNAME",
23
+ "PASSPORT",
24
+ "DRIVERSLICENSE"
25
+ ],
26
+ "num_train_examples": 500000,
27
+ "num_val_examples": 8000,
28
+ "batch_size": 64,
29
+ "grad_accum": 1,
30
+ "max_train_length": 384,
31
+ "learning_rate": 0.0004,
32
+ "warmup_steps": 800,
33
+ "max_epochs": 3,
34
+ "weight_decay": 0.01,
35
+ "max_grad_norm": 1.0,
36
+ "label_smoothing": 0.05,
37
+ "focal_gamma": 2.0,
38
+ "seed": 42,
39
+ "output_dir": "/vol/context_filter_v2"
40
+ }
generation_config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 50256,
3
+ "eos_token_id": 50256,
4
+ "pad_token_id": 50256,
5
+ "transformers_version": "4.40.0",
6
+ "id2label": {
7
+ "0": "O",
8
+ "1": "B-PERSON",
9
+ "2": "I-PERSON",
10
+ "3": "B-EMAIL",
11
+ "4": "I-EMAIL",
12
+ "5": "B-PHONE",
13
+ "6": "I-PHONE",
14
+ "7": "B-ADDRESS",
15
+ "8": "I-ADDRESS",
16
+ "9": "B-SSN",
17
+ "10": "I-SSN",
18
+ "11": "B-CREDITCARD",
19
+ "12": "I-CREDITCARD",
20
+ "13": "B-IP",
21
+ "14": "I-IP",
22
+ "15": "B-DATE",
23
+ "16": "I-DATE",
24
+ "17": "B-ORG",
25
+ "18": "I-ORG",
26
+ "19": "B-USERNAME",
27
+ "20": "I-USERNAME",
28
+ "21": "B-PASSPORT",
29
+ "22": "I-PASSPORT",
30
+ "23": "B-DRIVERSLICENSE",
31
+ "24": "I-DRIVERSLICENSE"
32
+ },
33
+ "label2id": {
34
+ "O": 0,
35
+ "B-PERSON": 1,
36
+ "I-PERSON": 2,
37
+ "B-EMAIL": 3,
38
+ "I-EMAIL": 4,
39
+ "B-PHONE": 5,
40
+ "I-PHONE": 6,
41
+ "B-ADDRESS": 7,
42
+ "I-ADDRESS": 8,
43
+ "B-SSN": 9,
44
+ "I-SSN": 10,
45
+ "B-CREDITCARD": 11,
46
+ "I-CREDITCARD": 12,
47
+ "B-IP": 13,
48
+ "I-IP": 14,
49
+ "B-DATE": 15,
50
+ "I-DATE": 16,
51
+ "B-ORG": 17,
52
+ "I-ORG": 18,
53
+ "B-USERNAME": 19,
54
+ "I-USERNAME": 20,
55
+ "B-PASSPORT": 21,
56
+ "I-PASSPORT": 22,
57
+ "B-DRIVERSLICENSE": 23,
58
+ "I-DRIVERSLICENSE": 24
59
+ }
60
+ }
label_map.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "label2id": {
3
+ "O": 0,
4
+ "B-PERSON": 1,
5
+ "I-PERSON": 2,
6
+ "B-EMAIL": 3,
7
+ "I-EMAIL": 4,
8
+ "B-PHONE": 5,
9
+ "I-PHONE": 6,
10
+ "B-ADDRESS": 7,
11
+ "I-ADDRESS": 8,
12
+ "B-SSN": 9,
13
+ "I-SSN": 10,
14
+ "B-CREDITCARD": 11,
15
+ "I-CREDITCARD": 12,
16
+ "B-IP": 13,
17
+ "I-IP": 14,
18
+ "B-DATE": 15,
19
+ "I-DATE": 16,
20
+ "B-ORG": 17,
21
+ "I-ORG": 18,
22
+ "B-USERNAME": 19,
23
+ "I-USERNAME": 20,
24
+ "B-PASSPORT": 21,
25
+ "I-PASSPORT": 22,
26
+ "B-DRIVERSLICENSE": 23,
27
+ "I-DRIVERSLICENSE": 24
28
+ },
29
+ "id2label": {
30
+ "0": "O",
31
+ "1": "B-PERSON",
32
+ "2": "I-PERSON",
33
+ "3": "B-EMAIL",
34
+ "4": "I-EMAIL",
35
+ "5": "B-PHONE",
36
+ "6": "I-PHONE",
37
+ "7": "B-ADDRESS",
38
+ "8": "I-ADDRESS",
39
+ "9": "B-SSN",
40
+ "10": "I-SSN",
41
+ "11": "B-CREDITCARD",
42
+ "12": "I-CREDITCARD",
43
+ "13": "B-IP",
44
+ "14": "I-IP",
45
+ "15": "B-DATE",
46
+ "16": "I-DATE",
47
+ "17": "B-ORG",
48
+ "18": "I-ORG",
49
+ "19": "B-USERNAME",
50
+ "20": "I-USERNAME",
51
+ "21": "B-PASSPORT",
52
+ "22": "I-PASSPORT",
53
+ "23": "B-DRIVERSLICENSE",
54
+ "24": "I-DRIVERSLICENSE"
55
+ }
56
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b0fc790777917ec18ed225ebaf716c08799ce0d9e79175564a7d6036e90b264
3
+ size 244589608
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>",
5
+ "pad_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": false,
8
+ "local_files_only": false,
9
+ "model_max_length": 1024,
10
+ "pad_token": "<|endoftext|>",
11
+ "tokenizer_class": "GPT2Tokenizer",
12
+ "unk_token": "<|endoftext|>"
13
+ }