AraBERT-summarization-goud / tokenizer_config.json
issam9's picture
add tokenizer
cbe7f62
raw
history blame
468 Bytes
{"do_lower_case": false, "do_basic_tokenize": true, "never_split": ["[بريد]", "[مستخدم]", "[رابط]"], "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": "aubmindlab/bert-large-arabertv02-twitter", "use_fast": true, "tokenizer_file": null, "tokenizer_class": "BertTokenizer"}