Hugging Face's logo

cuongdz01
/
layoutlm-cord-1

Token Classification
Transformers
TensorBoard
Safetensors
layoutlm
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
cuongdz01 commited on
Commit
44dcb01
•
1 Parent(s): 0b4d370

End of training

Browse files
Files changed (8) hide show
  1. README.md +0 -0
  2. logs/events.out.tfevents.1704168420.b07f080e9bbc.26.0 +2 -2
  3. model.safetensors +1 -1
  4. preprocessor_config.json +14 -0
  5. special_tokens_map.json +37 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +79 -0
  8. vocab.txt +0 -0
README.md ADDED
The diff for this file is too large to render. See raw diff
 
logs/events.out.tfevents.1704168420.b07f080e9bbc.26.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbba9c86961f59b6d169ff80cb9b7a57900a07a9fa50a7b8ecae86df2097ff2c
3
- size 37664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3f03a0dd940c02a35f6da89b1058eaecee1cd2034a7e40f5645d0f6e8479e62
3
+ size 39340
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eaebd816de1818db658adfa1fde7a81a361b2310a62c017f3ddd003bffb31c89
3
  size 450625884
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a63a613942b84e22e3d4bd95db93a3a849dfde74c80153c28d6af58220825f6b
3
  size 450625884
preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_ocr": true,
3
+ "do_resize": true,
4
+ "feature_extractor_type": "LayoutLMv2FeatureExtractor",
5
+ "image_processor_type": "LayoutLMv2ImageProcessor",
6
+ "ocr_lang": null,
7
+ "processor_class": "LayoutLMv2Processor",
8
+ "resample": 2,
9
+ "size": {
10
+ "height": 224,
11
+ "width": 224
12
+ },
13
+ "tesseract_config": ""
14
+ }
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 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "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
+ "additional_special_tokens": [],
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "cls_token_box": [
48
+ 0,
49
+ 0,
50
+ 0,
51
+ 0
52
+ ],
53
+ "do_basic_tokenize": true,
54
+ "do_lower_case": true,
55
+ "mask_token": "[MASK]",
56
+ "model_max_length": 512,
57
+ "never_split": null,
58
+ "only_label_first_subword": true,
59
+ "pad_token": "[PAD]",
60
+ "pad_token_box": [
61
+ 0,
62
+ 0,
63
+ 0,
64
+ 0
65
+ ],
66
+ "pad_token_label": -100,
67
+ "processor_class": "LayoutLMv2Processor",
68
+ "sep_token": "[SEP]",
69
+ "sep_token_box": [
70
+ 1000,
71
+ 1000,
72
+ 1000,
73
+ 1000
74
+ ],
75
+ "strip_accents": null,
76
+ "tokenize_chinese_chars": true,
77
+ "tokenizer_class": "LayoutLMv2Tokenizer",
78
+ "unk_token": "[UNK]"
79
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff