GWW / tokenizer_config.json
dunlp's picture
add tokenizer
1c5e106
raw
history blame contribute delete
546 Bytes
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": "/root/.cache/huggingface/transformers/adb82a117c09b0f8768357de8e836a9e0610730782f82edc49dd0020c48f1d03.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "GroNLP/bert-base-dutch-cased", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}