End of training
Browse files- preprocessor_config.json +1 -1
- tokenizer.json +2 -16
- tokenizer_config.json +7 -0
preprocessor_config.json
CHANGED
|
@@ -11,7 +11,7 @@
|
|
| 11 |
"data_format",
|
| 12 |
"input_data_format"
|
| 13 |
],
|
| 14 |
-
"apply_ocr":
|
| 15 |
"do_resize": true,
|
| 16 |
"image_processor_type": "LayoutLMv2ImageProcessor",
|
| 17 |
"ocr_lang": null,
|
|
|
|
| 11 |
"data_format",
|
| 12 |
"input_data_format"
|
| 13 |
],
|
| 14 |
+
"apply_ocr": false,
|
| 15 |
"do_resize": true,
|
| 16 |
"image_processor_type": "LayoutLMv2ImageProcessor",
|
| 17 |
"ocr_lang": null,
|
tokenizer.json
CHANGED
|
@@ -1,21 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
| 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
|
@@ -54,9 +54,11 @@
|
|
| 54 |
"do_basic_tokenize": true,
|
| 55 |
"do_lower_case": true,
|
| 56 |
"mask_token": "[MASK]",
|
|
|
|
| 57 |
"model_max_length": 512,
|
| 58 |
"never_split": null,
|
| 59 |
"only_label_first_subword": true,
|
|
|
|
| 60 |
"pad_token": "[PAD]",
|
| 61 |
"pad_token_box": [
|
| 62 |
0,
|
|
@@ -65,6 +67,8 @@
|
|
| 65 |
0
|
| 66 |
],
|
| 67 |
"pad_token_label": -100,
|
|
|
|
|
|
|
| 68 |
"processor_class": "LayoutLMv2Processor",
|
| 69 |
"sep_token": "[SEP]",
|
| 70 |
"sep_token_box": [
|
|
@@ -73,8 +77,11 @@
|
|
| 73 |
1000,
|
| 74 |
1000
|
| 75 |
],
|
|
|
|
| 76 |
"strip_accents": null,
|
| 77 |
"tokenize_chinese_chars": true,
|
| 78 |
"tokenizer_class": "LayoutLMv2Tokenizer",
|
|
|
|
|
|
|
| 79 |
"unk_token": "[UNK]"
|
| 80 |
}
|
|
|
|
| 54 |
"do_basic_tokenize": true,
|
| 55 |
"do_lower_case": true,
|
| 56 |
"mask_token": "[MASK]",
|
| 57 |
+
"max_length": 512,
|
| 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 |
}
|