layoutlmv3-test / tokenizer_config.json
mathieu1256's picture
End of training
9c74c3b verified
{
"add_prefix_space": true,
"added_tokens_decoder": {
"0": {
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<pad>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"50264": {
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"apply_ocr": false,
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"cls_token_box": [
0,
0,
0,
0
],
"eos_token": "</s>",
"errors": "replace",
"mask_token": "<mask>",
"model_max_length": 512,
"only_label_first_subword": true,
"pad_token": "<pad>",
"pad_token_box": [
0,
0,
0,
0
],
"pad_token_label": -100,
"processor_class": "LayoutLMv3Processor",
"sep_token": "</s>",
"sep_token_box": [
0,
0,
0,
0
],
"tokenizer_class": "LayoutLMv3Tokenizer",
"trim_offsets": true,
"unk_token": "<unk>",
"use_fast": true
}