Hugging Face's logo

nam194
/
resume_parsing_layoutlmv3

Token Classification
Transformers
PyTorch
layoutlmv3
Inference Endpoints
Model card Files Community
1
nam194 commited on
Commit
a904007
•
1 Parent(s): be625bb

commit files to HF hub

Browse files
Files changed (8) hide show
  1. config.json +84 -0
  2. merges.txt +0 -0
  3. preprocessor_config.json +27 -0
  4. pytorch_model.bin +3 -0
  5. special_tokens_map.json +51 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +86 -0
  8. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/layoutlmv3-large",
3
+ "architectures": [
4
+ "LayoutLMv3ForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "coordinate_size": 171,
10
+ "eos_token_id": 2,
11
+ "has_relative_attention_bias": true,
12
+ "has_spatial_attention_bias": true,
13
+ "hidden_act": "gelu",
14
+ "hidden_dropout_prob": 0.1,
15
+ "hidden_size": 1024,
16
+ "id2label": {
17
+ "0": "person_name",
18
+ "1": "dob_key",
19
+ "2": "dob_value",
20
+ "3": "gender_key",
21
+ "4": "gender_value",
22
+ "5": "phonenumber_key",
23
+ "6": "phonenumber_value",
24
+ "7": "email_key",
25
+ "8": "email_value",
26
+ "9": "address_key",
27
+ "10": "address_value",
28
+ "11": "socical_address_value",
29
+ "12": "education",
30
+ "13": "education_name",
31
+ "14": "education_time",
32
+ "15": "experience",
33
+ "16": "experience_name",
34
+ "17": "experience_time",
35
+ "18": "information",
36
+ "19": "undefined"
37
+ },
38
+ "initializer_range": 0.02,
39
+ "input_size": 224,
40
+ "intermediate_size": 4096,
41
+ "label2id": {
42
+ "address_key": 9,
43
+ "address_value": 10,
44
+ "dob_key": 1,
45
+ "dob_value": 2,
46
+ "education": 12,
47
+ "education_name": 13,
48
+ "education_time": 14,
49
+ "email_key": 7,
50
+ "email_value": 8,
51
+ "experience": 15,
52
+ "experience_name": 16,
53
+ "experience_time": 17,
54
+ "gender_key": 3,
55
+ "gender_value": 4,
56
+ "information": 18,
57
+ "person_name": 0,
58
+ "phonenumber_key": 5,
59
+ "phonenumber_value": 6,
60
+ "socical_address_value": 11,
61
+ "undefined": 19
62
+ },
63
+ "layer_norm_eps": 1e-05,
64
+ "max_2d_position_embeddings": 1024,
65
+ "max_position_embeddings": 514,
66
+ "max_rel_2d_pos": 256,
67
+ "max_rel_pos": 128,
68
+ "model_type": "layoutlmv3",
69
+ "num_attention_heads": 16,
70
+ "num_channels": 3,
71
+ "num_hidden_layers": 24,
72
+ "pad_token_id": 1,
73
+ "patch_size": 16,
74
+ "rel_2d_pos_bins": 64,
75
+ "rel_pos_bins": 32,
76
+ "second_input_size": 112,
77
+ "shape_size": 170,
78
+ "text_embed": true,
79
+ "torch_dtype": "float32",
80
+ "transformers_version": "4.27.4",
81
+ "type_vocab_size": 1,
82
+ "visual_embed": true,
83
+ "vocab_size": 50265
84
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_ocr": false,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "feature_extractor_type": "LayoutLMv3FeatureExtractor",
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "LayoutLMv3ImageProcessor",
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "ocr_lang": null,
19
+ "processor_class": "LayoutLMv3Processor",
20
+ "resample": 2,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "height": 224,
24
+ "width": 224
25
+ },
26
+ "tesseract_config": ""
27
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a8b7df5fa7b774ea174f059fa838914ef41c7c6afab34ef87402c0add4897a2
3
+ size 1428448113
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "apply_ocr": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "cls_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "cls_token_box": [
21
+ 0,
22
+ 0,
23
+ 0,
24
+ 0
25
+ ],
26
+ "eos_token": {
27
+ "__type": "AddedToken",
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "errors": "replace",
35
+ "mask_token": {
36
+ "__type": "AddedToken",
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false
42
+ },
43
+ "model_max_length": 512,
44
+ "only_label_first_subword": true,
45
+ "pad_token": {
46
+ "__type": "AddedToken",
47
+ "content": "<pad>",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
+ "pad_token_box": [
54
+ 0,
55
+ 0,
56
+ 0,
57
+ 0
58
+ ],
59
+ "pad_token_label": -100,
60
+ "processor_class": "LayoutLMv3Processor",
61
+ "sep_token": {
62
+ "__type": "AddedToken",
63
+ "content": "</s>",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false
68
+ },
69
+ "sep_token_box": [
70
+ 0,
71
+ 0,
72
+ 0,
73
+ 0
74
+ ],
75
+ "special_tokens_map_file": null,
76
+ "tokenizer_class": "LayoutLMv3Tokenizer",
77
+ "trim_offsets": true,
78
+ "unk_token": {
79
+ "__type": "AddedToken",
80
+ "content": "<unk>",
81
+ "lstrip": false,
82
+ "normalized": true,
83
+ "rstrip": false,
84
+ "single_word": false
85
+ }
86
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff