layoutlm-vqa / tokenizer_config.json
pardeepSF's picture
previous model
cec27ac
raw
history blame
532 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"max_len": 512,
"name_or_path": "microsoft/layoutlm-large-uncased",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "data/models/models--microsoft--layoutlm-large-uncased/snapshots/1e7d50dced3cdfea3a3d63c610e2aab36933dbef/special_tokens_map.json",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}