layoutlmv2_finetuned_docvqa / tokenizer_config.json
kanansharmaa's picture
Training in progress, step 200
cfb3882 verified
{
"added_tokens_decoder": {
"0": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"101": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"102": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"103": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [],
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"cls_token_box": [
0,
0,
0,
0
],
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 512,
"never_split": null,
"only_label_first_subword": true,
"pad_token": "[PAD]",
"pad_token_box": [
0,
0,
0,
0
],
"pad_token_label": -100,
"processor_class": "LayoutLMv2Processor",
"sep_token": "[SEP]",
"sep_token_box": [
1000,
1000,
1000,
1000
],
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "LayoutLMv2Tokenizer",
"unk_token": "[UNK]"
}