lmv2-g-rai2-732-doc-10-07 / tokenizer_config.json
Sebabrata's picture
Training in progress, epoch 1
491358a
raw
history blame
693 Bytes
{
"additional_special_tokens": null,
"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,
"name_or_path": "microsoft/layoutlmv2-base-uncased",
"never_split": null,
"only_label_first_subword": true,
"pad_token": "[PAD]",
"pad_token_box": [
0,
0,
0,
0
],
"pad_token_label": -100,
"sep_token": "[SEP]",
"sep_token_box": [
1000,
1000,
1000,
1000
],
"special_tokens_map_file": null,
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "LayoutLMv2Tokenizer",
"unk_token": "[UNK]"
}