layoutlm-custom / tokenizer_config.json
tanay
add tokenizer
7fc2dd0
{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "max_len": 512, "model_max_length": 512, "special_tokens_map_file": "/root/.cache/huggingface/transformers/48c3f426580c1b3278dbebb8c8dd372ea1549792f092b4f6fae1e21881c2cbd9.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "tokenizer_file": "/root/.cache/huggingface/transformers/78de759d8c688ac51b32f20d922ca1c1c3dbec5f9b3abbe9f3fcca22b815249f.7f2721073f19841be16f41b0a70b600ca6b880c8f3df6f3535cbc704371bdfa4", "name_or_path": "microsoft/layoutlm-base-uncased", "tokenizer_class": "LayoutLMTokenizer"}