english_news_classification_headlines / tokenizer_config.json
rafaelm47labs's picture
Files from the iptc english classifier
e6616dd
raw
history blame
373 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, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "dbmdz/bert-base-italian-cased", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}