OCR-LayoutLMv3 / tokenizer_config.json
jinhybr's picture
Training in progress, step 500
f494dfb
raw
history blame
1.67 kB
{
"add_prefix_space": true,
"apply_ocr": false,
"bos_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"cls_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"cls_token_box": [
0,
0,
0,
0
],
"eos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 512,
"name_or_path": "microsoft/layoutlmv3-base",
"only_label_first_subword": true,
"pad_token": {
"__type": "AddedToken",
"content": "<pad>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token_box": [
0,
0,
0,
0
],
"pad_token_label": -100,
"processor_class": "LayoutLMv3Processor",
"sep_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"sep_token_box": [
0,
0,
0,
0
],
"special_tokens_map_file": null,
"tokenizer_class": "LayoutLMv3Tokenizer",
"trim_offsets": true,
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}