xilpam commited on
Commit
e13ef40
·
verified ·
1 Parent(s): ad2dcbd

Upload processor

Browse files
Files changed (3) hide show
  1. README.md +1 -1
  2. tokenizer.json +2 -16
  3. tokenizer_config.json +6 -0
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  license: mit
3
- base_model: xilpam/layoutlm-funsd-tf
4
  tags:
5
  - generated_from_keras_callback
 
6
  model-index:
7
  - name: layoutlm-funsd-tf
8
  results: []
 
1
  ---
2
  license: mit
 
3
  tags:
4
  - generated_from_keras_callback
5
+ base_model: xilpam/layoutlm-funsd-tf
6
  model-index:
7
  - name: layoutlm-funsd-tf
8
  results: []
tokenizer.json CHANGED
@@ -1,21 +1,7 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 512,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
- "padding": {
10
- "strategy": {
11
- "Fixed": 512
12
- },
13
- "direction": "Right",
14
- "pad_to_multiple_of": null,
15
- "pad_id": 0,
16
- "pad_type_id": 0,
17
- "pad_token": "[PAD]"
18
- },
19
  "added_tokens": [
20
  {
21
  "id": 0,
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
tokenizer_config.json CHANGED
@@ -58,6 +58,7 @@
58
  "model_max_length": 512,
59
  "never_split": null,
60
  "only_label_first_subword": true,
 
61
  "pad_token": "[PAD]",
62
  "pad_token_box": [
63
  0,
@@ -66,6 +67,8 @@
66
  0
67
  ],
68
  "pad_token_label": -100,
 
 
69
  "processor_class": "LayoutLMv2Processor",
70
  "sep_token": "[SEP]",
71
  "sep_token_box": [
@@ -74,8 +77,11 @@
74
  1000,
75
  1000
76
  ],
 
77
  "strip_accents": null,
78
  "tokenize_chinese_chars": true,
79
  "tokenizer_class": "LayoutLMv2Tokenizer",
 
 
80
  "unk_token": "[UNK]"
81
  }
 
58
  "model_max_length": 512,
59
  "never_split": null,
60
  "only_label_first_subword": true,
61
+ "pad_to_multiple_of": null,
62
  "pad_token": "[PAD]",
63
  "pad_token_box": [
64
  0,
 
67
  0
68
  ],
69
  "pad_token_label": -100,
70
+ "pad_token_type_id": 0,
71
+ "padding_side": "right",
72
  "processor_class": "LayoutLMv2Processor",
73
  "sep_token": "[SEP]",
74
  "sep_token_box": [
 
77
  1000,
78
  1000
79
  ],
80
+ "stride": 0,
81
  "strip_accents": null,
82
  "tokenize_chinese_chars": true,
83
  "tokenizer_class": "LayoutLMv2Tokenizer",
84
+ "truncation_side": "right",
85
+ "truncation_strategy": "longest_first",
86
  "unk_token": "[UNK]"
87
  }